# Single-photon Image Super-resolution via Self-supervised Learning

arXiv: https://arxiv.org/abs/2303.02033 · HTML: https://mlsanity.com/paper/2303.02033/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Harmonic Networks: Deep Translation and Rotation Equivariance](https://mlsanity.com/paper/1612.04642/) (2016)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [Equivariant Imaging: Learning Beyond the Range Space](https://mlsanity.com/paper/2103.14756/) (2021)
- [Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements](https://mlsanity.com/paper/2111.12855/) (2021)
- [Asynchronous Single-Photon 3D Imaging](https://mlsanity.com/paper/1908.06372/) (2019)
- [Single-photon imaging over 200 km](https://mlsanity.com/paper/2103.05860/) (2021)
- [Robust super-resolution depth imaging via a multi-feature fusion deep network](https://mlsanity.com/paper/2011.11444/) (2020)
- [Super-resolution single-photon imaging at 8.2 kilometers](https://mlsanity.com/paper/2001.11450/) (2020)
- [Robust photon-efficient imaging using a pixel-wise residual shrinkage network](https://mlsanity.com/paper/2201.01453/) (2022)
- [Deep Domain Adversarial Adaptation for Photon-efficient Imaging](https://mlsanity.com/paper/2201.02475/) (2022)

## Built on by (most cited first, 1 of 1)

- [Equivariant Multi-Modality Image Fusion](https://mlsanity.com/paper/2305.11443/) (2023)

## Abstract (arXiv)

Single-Photon Image Super-Resolution (SPISR) aims to recover a high-resolution volumetric photon counting cube from a noisy low-resolution one by computational imaging algorithms. In real-world scenarios, pairs of training samples are often expensive or impossible to obtain. By extending Equivariant Imaging (EI) to volumetric single-photon data, we propose a self-supervised learning framework for the SPISR task. Particularly, using the Poisson unbiased Kullback-Leibler risk estimator and equivariance, our method is able to learn from noisy measurements without ground truths. Comprehensive experiments on simulated and real-world dataset demonstrate that the proposed method achieves comparable performance with supervised learning and outperforms interpolation-based methods.